[Test][e2e][LoRA] Add more e2e tests to cover scenarios of LoRA by paulyu12 · Pull Request #4075 · vllm-project/vllm-ascend

paulyu12 · 2025-11-10T02:39:33Z

What this PR does / why we need it?

This PR depends on PR #4046. And only if the latter merged, it will work.

This PR aims to solve the issue #3240.

The new-added Llama-2-7b-hf and Qwen3-0.6B testcases will cover the senarios that the LoRA weights are added to q_proj, v_proj, k_proj, o_proj, gate_proj, up_proj, down_proj, embed_tokens and lm_head modules.

Does this PR introduce any user-facing change?

No.

How was this patch tested?

pytest -sv tests/e2e/singlecard/test_llama2_lora.py
pytest -sv tests/e2e/singlecard/test_qwen3_multi_loras.py

vLLM version: v0.11.0
vLLM main: vllm-project/vllm@83f478b

github-actions · 2025-11-10T02:39:43Z

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

A PR should do only one thing, smaller PRs enable faster reviews.
Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.

gemini-code-assist

Code Review

This pull request adds end-to-end tests for LoRA scenarios. The changes are mostly good, but I've found a high-severity issue in tests/e2e/singlecard/test_qwen3_multi_loras.py related to test isolation. The test uses mutable global state, which can lead to flaky and hard-to-maintain tests. I've provided a refactoring suggestion to address this by encapsulating the state within the test function. This will make the test self-contained and robust.

github-actions · 2025-12-01T11:06:28Z

This pull request has conflicts, please resolve those before we can evaluate the pull request.

github-actions · 2025-12-24T14:10:30Z

This pull request has conflicts, please resolve those before we can evaluate the pull request.

wangxiyuan · 2026-01-05T03:33:48Z

@paulyu12 any update?

paulyu12 · 2026-01-05T03:50:32Z

@paulyu12 any update?

This CI issue was introduced by #4168 .I tried according to your instruction (Don't make LoRA scenario go into this if condition statement), but it never works.

I am still working on this.

wangxiyuan · 2026-01-05T06:09:26Z

@wxsIcey please take a look

github-actions · 2026-01-09T08:01:40Z

This pull request has conflicts, please resolve those before we can evaluate the pull request.

Signed-off-by: paulyu12 <507435917@qq.com>

…to eplb_refactor * 'main' of https://github.com/vllm-project/vllm-ascend: [CI] Fix lint CI (vllm-project#5880) [Feature] implement eagle spec decoding for model runner v2 (vllm-project#5840) [Quantization] Support compressed tensors moe w8a8 int8 dynamic weight (vllm-project#5718) [EPLB][Bugfix] Get expert map from layers (vllm-project#5817) [Bugfix] Fixed an accuracy problem of sp with eagle3 (vllm-project#5816) [P/D] bugfix for p node force free requset (vllm-project#5431) [Lint]Style: Convert `example` to `ruff format` (vllm-project#5863) [Main2Main] Upgrade vllm commit to 0109 (vllm-project#5752) [Bugfix][P/D] fix layerwise connector for decoder tp size > num kv heads (vllm-project#5846) [Test][e2e][LoRA] Add more e2e tests to cover scenarios of LoRA (vllm-project#4075) [CustomOp][Perf] Merge Q/K split to simplify AscendApplyRotaryEmb for better performance (vllm-project#5799) [Lint]Style: Convert `root`, `benchmarks`, `tools` and `docs` to `ruff format` (vllm-project#5843) enable ep32 for dispatch_ffn_combine (vllm-project#5787)

…-project#4075) ### What this PR does / why we need it? This PR depends on PR vllm-project#4046. And only if the latter merged, it will work. This PR aims to solve the issue vllm-project#3240. The new-added Llama-2-7b-hf and Qwen3-0.6B testcases will cover the senarios that the LoRA weights are added to q_proj, v_proj, k_proj, o_proj, gate_proj, up_proj, down_proj, embed_tokens and lm_head modules. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? pytest -sv tests/e2e/singlecard/test_llama2_lora.py pytest -sv tests/e2e/singlecard/test_qwen3_multi_loras.py - vLLM version: v0.11.0 - vLLM main: vllm-project/vllm@83f478b --------- Signed-off-by: paulyu12 <507435917@qq.com>

…-project#4075) ### What this PR does / why we need it? This PR depends on PR vllm-project#4046. And only if the latter merged, it will work. This PR aims to solve the issue vllm-project#3240. The new-added Llama-2-7b-hf and Qwen3-0.6B testcases will cover the senarios that the LoRA weights are added to q_proj, v_proj, k_proj, o_proj, gate_proj, up_proj, down_proj, embed_tokens and lm_head modules. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? pytest -sv tests/e2e/singlecard/test_llama2_lora.py pytest -sv tests/e2e/singlecard/test_qwen3_multi_loras.py - vLLM version: v0.11.0 - vLLM main: vllm-project/vllm@83f478b --------- Signed-off-by: paulyu12 <507435917@qq.com> Signed-off-by: zrj026 <zhangrunjiang026@gmail.com>

…-project#4075) ### What this PR does / why we need it? This PR depends on PR vllm-project#4046. And only if the latter merged, it will work. This PR aims to solve the issue vllm-project#3240. The new-added Llama-2-7b-hf and Qwen3-0.6B testcases will cover the senarios that the LoRA weights are added to q_proj, v_proj, k_proj, o_proj, gate_proj, up_proj, down_proj, embed_tokens and lm_head modules. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? pytest -sv tests/e2e/singlecard/test_llama2_lora.py pytest -sv tests/e2e/singlecard/test_qwen3_multi_loras.py - vLLM version: v0.11.0 - vLLM main: vllm-project/vllm@83f478b --------- Signed-off-by: paulyu12 <507435917@qq.com>

…-project#4075) ### What this PR does / why we need it? This PR depends on PR vllm-project#4046. And only if the latter merged, it will work. This PR aims to solve the issue vllm-project#3240. The new-added Llama-2-7b-hf and Qwen3-0.6B testcases will cover the senarios that the LoRA weights are added to q_proj, v_proj, k_proj, o_proj, gate_proj, up_proj, down_proj, embed_tokens and lm_head modules. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? pytest -sv tests/e2e/singlecard/test_llama2_lora.py pytest -sv tests/e2e/singlecard/test_qwen3_multi_loras.py - vLLM version: v0.11.0 - vLLM main: vllm-project/vllm@83f478b --------- Signed-off-by: paulyu12 <507435917@qq.com> Signed-off-by: zrj026 <zhangrunjiang026@gmail.com>

…-project#4075) ### What this PR does / why we need it? This PR depends on PR vllm-project#4046. And only if the latter merged, it will work. This PR aims to solve the issue vllm-project#3240. The new-added Llama-2-7b-hf and Qwen3-0.6B testcases will cover the senarios that the LoRA weights are added to q_proj, v_proj, k_proj, o_proj, gate_proj, up_proj, down_proj, embed_tokens and lm_head modules. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? pytest -sv tests/e2e/singlecard/test_llama2_lora.py pytest -sv tests/e2e/singlecard/test_qwen3_multi_loras.py - vLLM version: v0.11.0 - vLLM main: vllm-project/vllm@83f478b --------- Signed-off-by: paulyu12 <507435917@qq.com>

github-actions bot added the module:tests label Nov 10, 2025

gemini-code-assist bot reviewed Nov 10, 2025

View reviewed changes

Comment thread tests/e2e/singlecard/test_qwen3_multi_loras.py Outdated

paulyu12 added ready read for review ready-for-test start test by label for PR labels Nov 11, 2025

github-actions bot added the merge-conflicts label Dec 1, 2025

github-actions bot removed the merge-conflicts label Dec 19, 2025

paulyu12 force-pushed the lora_llama_testcase branch from a0b213b to b2a1cb8 Compare December 22, 2025 09:04

paulyu12 added ready read for review ready-for-test start test by label for PR and removed ready read for review ready-for-test start test by label for PR labels Dec 22, 2025

github-actions bot added the merge-conflicts label Dec 24, 2025

Yikun mentioned this pull request Dec 28, 2025

[Bug]: bf16 lora don't work with 0.11.0rc2 #5021

Closed

paulyu12 added ready read for review ready-for-test start test by label for PR and removed ready read for review ready-for-test start test by label for PR labels Jan 8, 2026

github-actions bot removed the merge-conflicts label Jan 9, 2026

paulyu12 removed ready read for review ready-for-test start test by label for PR labels Jan 9, 2026

paulyu12 added ready read for review ready-for-test start test by label for PR labels Jan 9, 2026

github-actions bot added the merge-conflicts label Jan 9, 2026

github-actions bot removed the merge-conflicts label Jan 9, 2026

paulyu12 added ready read for review ready-for-test start test by label for PR and removed ready read for review ready-for-test start test by label for PR labels Jan 9, 2026

add lora e2d testcase

825e2d2

Signed-off-by: paulyu12 <507435917@qq.com>

paulyu12 force-pushed the lora_llama_testcase branch from 142c570 to 825e2d2 Compare January 12, 2026 03:10

add lora e2d testcase

4ae6afd

Signed-off-by: paulyu12 <507435917@qq.com>

paulyu12 added ready read for review ready-for-test start test by label for PR and removed ready read for review ready-for-test start test by label for PR labels Jan 12, 2026

wangxiyuan approved these changes Jan 13, 2026

View reviewed changes

paulyu12 merged commit 5b95c6b into vllm-project:main Jan 13, 2026
61 of 62 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[Test][e2e][LoRA] Add more e2e tests to cover scenarios of LoRA#4075

[Test][e2e][LoRA] Add more e2e tests to cover scenarios of LoRA#4075
paulyu12 merged 2 commits intovllm-project:mainfrom
paulyu12:lora_llama_testcase

paulyu12 commented Nov 10, 2025 •

edited by github-actions bot

Loading

Uh oh!

github-actions bot commented Nov 10, 2025

Uh oh!

gemini-code-assist bot left a comment

Uh oh!

Uh oh!

github-actions bot commented Dec 1, 2025

Uh oh!

github-actions bot commented Dec 24, 2025

Uh oh!

wangxiyuan commented Jan 5, 2026

Uh oh!

paulyu12 commented Jan 5, 2026

Uh oh!

wangxiyuan commented Jan 5, 2026

Uh oh!

github-actions bot commented Jan 9, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

paulyu12 commented Nov 10, 2025 • edited by github-actions bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

What this PR does / why we need it?

Does this PR introduce any user-facing change?

How was this patch tested?

Uh oh!

github-actions bot commented Nov 10, 2025

Uh oh!

gemini-code-assist bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

Uh oh!

github-actions bot commented Dec 1, 2025

Uh oh!

github-actions bot commented Dec 24, 2025

Uh oh!

wangxiyuan commented Jan 5, 2026

Uh oh!

paulyu12 commented Jan 5, 2026

Uh oh!

wangxiyuan commented Jan 5, 2026

Uh oh!

github-actions bot commented Jan 9, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

paulyu12 commented Nov 10, 2025 •

edited by github-actions bot

Loading